Model: GPT-2 Small: 12 Layers, 3072 Neurons per Layer

Dataset: Open Web Text

Neuron 2906 in Layer 4

Load this data into an Interactive Neuroscope

See Documentation here

Hooked Transformer Loading: HookedTransformer.from_pretrained('gpt2-small')

Click the toggle to see the full text!

Text #0

Max Range: 4.0371. Min Range: -4.0371

Max Act: 4.0371. Min Act: -0.1700

Data Index: 763325 (Open Web Text)

Max Activating Token Index: 765

Text #1

Max Range: 4.0371. Min Range: -4.0371

Max Act: 4.0346. Min Act: -0.1700

Data Index: 8034042 (Open Web Text)

Max Activating Token Index: 11

Text #2

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.9760. Min Act: -0.1700

Data Index: 6160842 (Open Web Text)

Max Activating Token Index: 118

Text #3

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.9773. Min Act: -0.1700

Data Index: 4038279 (Open Web Text)

Max Activating Token Index: 434

Text #4

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.9414. Min Act: -0.1700

Data Index: 7027048 (Open Web Text)

Max Activating Token Index: 155

Text #5

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.9618. Min Act: -0.1700

Data Index: 7469840 (Open Web Text)

Max Activating Token Index: 816

Text #6

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.9289. Min Act: -0.1700

Data Index: 8788506 (Open Web Text)

Max Activating Token Index: 200

Text #7

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.9016. Min Act: -0.1700

Data Index: 5852029 (Open Web Text)

Max Activating Token Index: 212

Text #8

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.8333. Min Act: -0.1700

Data Index: 5509405 (Open Web Text)

Max Activating Token Index: 62

Text #9

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.8685. Min Act: -0.1700

Data Index: 1865174 (Open Web Text)

Max Activating Token Index: 790

Text #10

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.7901. Min Act: -0.1700

Data Index: 7947530 (Open Web Text)

Max Activating Token Index: 314

Text #11

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.8857. Min Act: -0.1700

Data Index: 576321 (Open Web Text)

Max Activating Token Index: 407

Text #12

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.8097. Min Act: -0.1700

Data Index: 716 (Open Web Text)

Max Activating Token Index: 763

Text #13

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.7814. Min Act: -0.1700

Data Index: 1439198 (Open Web Text)

Max Activating Token Index: 675

Text #14

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.7744. Min Act: -0.1700

Data Index: 890987 (Open Web Text)

Max Activating Token Index: 372

Text #15

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.8049. Min Act: -0.1700

Data Index: 8031705 (Open Web Text)

Max Activating Token Index: 444

Text #16

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.7900. Min Act: -0.1700

Data Index: 3244941 (Open Web Text)

Max Activating Token Index: 59

Text #17

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.8125. Min Act: -0.1700

Data Index: 6717778 (Open Web Text)

Max Activating Token Index: 556

Text #18

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.7733. Min Act: -0.1700

Data Index: 3004023 (Open Web Text)

Max Activating Token Index: 371

Text #19

Max Range: 4.0371. Min Range: -4.0371

Max Act: 3.7737. Min Act: -0.1700

Data Index: 2076880 (Open Web Text)

Max Activating Token Index: 826